| Who | When |
Messages | |
|
|
|
| Hamed Masnadi-Shirazi
|
1
|
 |
|
11-16-2004 01:36 AM ET (US)
|
|
Is the Model Structure learned as well or just the parameters of the imposed model structure?
|
| Stephen Krotosky
|
2
|
|
|
11-16-2004 02:27 AM ET (US)
|
|
Just the parameters. For example, in the face detection case, they decided to use derivative of gaussian filters and the training set's response to these filters is used to learn the model parameters.
|
| Rasit Topaloglu
|
3
|
|
|
11-16-2004 03:33 AM ET (US)
|
|
Edited by author 11-16-2004 03:46 AM
I have seen that spring-based models work quite well for a wide number of engineering applications
The detection of occluded images is important to prove for this type of a model (and is done in the paper experimentally). But they should also have done occluded images of people. Say we only see a person's body and head, it would be quite possible to confuse the person with other objects (like TV on a table). Some of these can be eliminated using the prior probabilities though by restricting the size of the persons.
|
| Robin Hewitt
|
4
|
|
|
11-16-2004 11:17 AM ET (US)
|
|
Edited by author 11-16-2004 11:18 AM
I was curious about the reasoning behind some of their choices. In particular, why the use of set (rather than centroid) distances, and why the choice of mahalanobis (rather than euclidean) metric for measuring grid displacements.
|
| |
Messages 5-6 deleted by topic administrator between 07-22-2006 02:06 AM and 07-21-2006 09:00 AM |
